Alert button
Picture for Florian Tramer

Florian Tramer

Alert button

Dj

Are aligned neural networks adversarially aligned?

Jun 26, 2023
Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Irena Gao, Anas Awadalla, Pang Wei Koh, Daphne Ippolito, Katherine Lee, Florian Tramer, Ludwig Schmidt

Figure 1 for Are aligned neural networks adversarially aligned?
Figure 2 for Are aligned neural networks adversarially aligned?
Figure 3 for Are aligned neural networks adversarially aligned?
Figure 4 for Are aligned neural networks adversarially aligned?
Viaarxiv icon

Increasing Confidence in Adversarial Robustness Evaluations

Jun 28, 2022
Roland S. Zimmermann, Wieland Brendel, Florian Tramer, Nicholas Carlini

Figure 1 for Increasing Confidence in Adversarial Robustness Evaluations
Figure 2 for Increasing Confidence in Adversarial Robustness Evaluations
Figure 3 for Increasing Confidence in Adversarial Robustness Evaluations
Figure 4 for Increasing Confidence in Adversarial Robustness Evaluations
Viaarxiv icon

The Privacy Onion Effect: Memorization is Relative

Jun 22, 2022
Nicholas Carlini, Matthew Jagielski, Chiyuan Zhang, Nicolas Papernot, Andreas Terzis, Florian Tramer

Figure 1 for The Privacy Onion Effect: Memorization is Relative
Figure 2 for The Privacy Onion Effect: Memorization is Relative
Figure 3 for The Privacy Onion Effect: Memorization is Relative
Figure 4 for The Privacy Onion Effect: Memorization is Relative
Viaarxiv icon

(Certified!!) Adversarial Robustness for Free!

Jun 21, 2022
Nicholas Carlini, Florian Tramer, Krishnamurthy, Dvijotham, J. Zico Kolter

Figure 1 for (Certified!!) Adversarial Robustness for Free!
Figure 2 for (Certified!!) Adversarial Robustness for Free!
Figure 3 for (Certified!!) Adversarial Robustness for Free!
Figure 4 for (Certified!!) Adversarial Robustness for Free!
Viaarxiv icon

Debugging Differential Privacy: A Case Study for Privacy Auditing

Mar 28, 2022
Florian Tramer, Andreas Terzis, Thomas Steinke, Shuang Song, Matthew Jagielski, Nicholas Carlini

Figure 1 for Debugging Differential Privacy: A Case Study for Privacy Auditing
Viaarxiv icon

Quantifying Memorization Across Neural Language Models

Feb 24, 2022
Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, Chiyuan Zhang

Figure 1 for Quantifying Memorization Across Neural Language Models
Figure 2 for Quantifying Memorization Across Neural Language Models
Figure 3 for Quantifying Memorization Across Neural Language Models
Figure 4 for Quantifying Memorization Across Neural Language Models
Viaarxiv icon

Membership Inference Attacks From First Principles

Dec 07, 2021
Nicholas Carlini, Steve Chien, Milad Nasr, Shuang Song, Andreas Terzis, Florian Tramer

Figure 1 for Membership Inference Attacks From First Principles
Figure 2 for Membership Inference Attacks From First Principles
Figure 3 for Membership Inference Attacks From First Principles
Figure 4 for Membership Inference Attacks From First Principles
Viaarxiv icon

Extracting Training Data from Large Language Models

Dec 14, 2020
Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom Brown, Dawn Song, Ulfar Erlingsson, Alina Oprea, Colin Raffel

Figure 1 for Extracting Training Data from Large Language Models
Figure 2 for Extracting Training Data from Large Language Models
Figure 3 for Extracting Training Data from Large Language Models
Figure 4 for Extracting Training Data from Large Language Models
Viaarxiv icon